Chris Lattner
|
5cdcc58d51
|
Add some folds for == and != comparisons. This allows us to
codegen this loop in stepanov:
no_exit.i: ; preds = %entry, %no_exit.i, %then.i, %_Z5checkd.exit
%i.0.0 = phi int [ 0, %entry ], [ %i.0.0, %no_exit.i ], [ %inc.0, %_Z5checkd.exit ], [ %inc.012, %then.i ] ; <int> [#uses=3]
%indvar = phi uint [ %indvar.next, %no_exit.i ], [ 0, %entry ], [ 0, %then.i ], [ 0, %_Z5checkd.exit ] ; <uint> [#uses=3]
%result_addr.i.0 = phi double [ %tmp.4.i.i, %no_exit.i ], [ 0.000000e+00, %entry ], [ 0.000000e+00, %then.i ], [ 0.000000e+00, %_Z5checkd.exit ] ; <double> [#uses=1]
%first_addr.0.i.2.rec = cast uint %indvar to int ; <int> [#uses=1]
%first_addr.0.i.2 = getelementptr [2000 x double]* %data, int 0, uint %indvar ; <double*> [#uses=1]
%inc.i.rec = add int %first_addr.0.i.2.rec, 1 ; <int> [#uses=1]
%inc.i = getelementptr [2000 x double]* %data, int 0, int %inc.i.rec ; <double*> [#uses=1]
%tmp.3.i.i = load double* %first_addr.0.i.2 ; <double> [#uses=1]
%tmp.4.i.i = add double %result_addr.i.0, %tmp.3.i.i ; <double> [#uses=2]
%tmp.2.i = seteq double* %inc.i, getelementptr ([2000 x double]* %data, int 0, int 2000) ; <bool> [#uses=1]
%indvar.next = add uint %indvar, 1 ; <uint> [#uses=1]
br bool %tmp.2.i, label %_Z10accumulateIPddET0_T_S2_S1_.exit, label %no_exit.i
To this:
.LBB_Z4testIPddEvT_S1_T0__1: # no_exit.i
fldl data(,%eax,8)
fldl 16(%esp)
faddp %st(1)
fstpl 16(%esp)
incl %eax
movl %eax, %ecx
shll $3, %ecx
cmpl $16000, %ecx
#FP_REG_KILL
jne .LBB_Z4testIPddEvT_S1_T0__1 # no_exit.i
instead of this:
.LBB_Z4testIPddEvT_S1_T0__1: # no_exit.i
fldl data(,%eax,8)
fldl 16(%esp)
faddp %st(1)
fstpl 16(%esp)
incl %eax
leal data(,%eax,8), %ecx
leal data+16000, %edx
cmpl %edx, %ecx
#FP_REG_KILL
jne .LBB_Z4testIPddEvT_S1_T0__1 # no_exit.i
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19425 91177308-0d34-0410-b5e6-96231b3b80d8
|
2005-01-09 20:52:51 +00:00 |
|
Chris Lattner
|
abd2182875
|
Add a simple transformation. This allows us to compile one of the inner
loops in stepanov to this:
.LBB_Z5test0PdS__2: # no_exit.1
fldl data(,%eax,8)
fldl 24(%esp)
faddp %st(1)
fstl 24(%esp)
incl %eax
cmpl $2000, %eax
fstpl 16(%esp)
#FP_REG_KILL
jl .LBB_Z5test0PdS__2
instead of this:
.LBB_Z5test0PdS__2: # no_exit.1
fldl data(,%eax,8)
fldl 24(%esp)
faddp %st(1)
fstl 24(%esp)
incl %eax
movl $data, %ecx
movl %ecx, %edx
addl $16000, %edx
subl %ecx, %edx
movl %edx, %ecx
sarl $2, %ecx
shrl $29, %ecx
addl %ecx, %edx
sarl $3, %edx
cmpl %edx, %eax
fstpl 16(%esp)
#FP_REG_KILL
jl .LBB_Z5test0PdS__2
The old instruction selector produced:
.LBB_Z5test0PdS__2: # no_exit.1
fldl 24(%esp)
faddl data(,%eax,8)
fstl 24(%esp)
movl %eax, %ecx
incl %ecx
incl %eax
leal data+16000, %edx
movl $data, %edi
subl %edi, %edx
movl %edx, %edi
sarl $2, %edi
shrl $29, %edi
addl %edi, %edx
sarl $3, %edx
cmpl %edx, %ecx
fstpl 16(%esp)
#FP_REG_KILL
jl .LBB_Z5test0PdS__2 # no_exit.1
Which is even worse!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@19419 91177308-0d34-0410-b5e6-96231b3b80d8
|
2005-01-09 20:09:57 +00:00 |
|
